sched/clock: Make local_clock() noinstr

With sched_clock() noinstr, provide a noinstr implementation of
local_clock().
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lore.kernel.org/r/20230126151323.760767043@infradead.org

include/linux/sched/clock.h

@@ -45,7 +45,7 @@ static inline u64 cpu_clock(int cpu)
 	return sched_clock();
 }
 
-static inline u64 local_clock(void)
+static __always_inline u64 local_clock(void)
 {
 	return sched_clock();
 }
@@ -79,10 +79,8 @@ static inline u64 cpu_clock(int cpu)
 	return sched_clock_cpu(cpu);
 }
 
-static inline u64 local_clock(void)
-{
-	return sched_clock_cpu(raw_smp_processor_id());
-}
+extern u64 local_clock(void);
+
 #endif
 
 #ifdef CONFIG_IRQ_TIME_ACCOUNTING

kernel/sched/clock.c

@@ -93,7 +93,7 @@ struct sched_clock_data {
 
 static DEFINE_PER_CPU_SHARED_ALIGNED(struct sched_clock_data, sched_clock_data);
 
-notrace static inline struct sched_clock_data *this_scd(void)
+static __always_inline struct sched_clock_data *this_scd(void)
 {
 	return this_cpu_ptr(&sched_clock_data);
 }
@@ -244,12 +244,12 @@ late_initcall(sched_clock_init_late);
  * min, max except they take wrapping into account
  */
 
-notrace static inline u64 wrap_min(u64 x, u64 y)
+static __always_inline u64 wrap_min(u64 x, u64 y)
 {
 	return (s64)(x - y) < 0 ? x : y;
 }
 
-notrace static inline u64 wrap_max(u64 x, u64 y)
+static __always_inline u64 wrap_max(u64 x, u64 y)
 {
 	return (s64)(x - y) > 0 ? x : y;
 }
@@ -260,7 +260,7 @@ notrace static inline u64 wrap_max(u64 x, u64 y)
  *  - filter out backward motion
  *  - use the GTOD tick value to create a window to filter crazy TSC values
  */
-notrace static u64 sched_clock_local(struct sched_clock_data *scd)
+static __always_inline u64 sched_clock_local(struct sched_clock_data *scd)
 {
 	u64 now, clock, old_clock, min_clock, max_clock, gtod;
 	s64 delta;
@@ -287,13 +287,28 @@ notrace static u64 sched_clock_local(struct sched_clock_data *scd)
 	clock = wrap_max(clock, min_clock);
 	clock = wrap_min(clock, max_clock);
 
-	if (!try_cmpxchg64(&scd->clock, &old_clock, clock))
+	if (!arch_try_cmpxchg64(&scd->clock, &old_clock, clock))
 		goto again;
 
 	return clock;
 }
 
-notrace static u64 sched_clock_remote(struct sched_clock_data *scd)
+noinstr u64 local_clock(void)
+{
+	u64 clock;
+
+	if (static_branch_likely(&__sched_clock_stable))
+		return sched_clock() + __sched_clock_offset;
+
+	preempt_disable_notrace();
+	clock = sched_clock_local(this_scd());
+	preempt_enable_notrace();
+
+	return clock;
+}
+EXPORT_SYMBOL_GPL(local_clock);
+
+static notrace u64 sched_clock_remote(struct sched_clock_data *scd)
 {
 	struct sched_clock_data *my_scd = this_scd();
 	u64 this_clock, remote_clock;